The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local Python script located at ../okf/scripts/validate_okf.py to validate the generated output bundle.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted documentation, notes, and wikis which may contain embedded instructions that the agent might follow.
Ingestion points: The <src> source directory containing notes and documentation as described in SKILL.md.
Boundary markers: Absent; the skill does not provide delimiters or instructions to the agent to disregard instructions found within the source documents.
Capability inventory: File writing to the <out> directory and execution of the validate_okf.py Python script.
Sanitization: Absent; the skill does not implement filtering, escaping, or validation of the input content before processing it.

okf-refactor